Feb 26, 2020   9:13 p.m. Viktor
Academic information system

Persons at STU


This page displays all publicly accessible information about the desired person. Some information about the person's occupation and offices may be hidden.

prof. Ing. Štefan Kozák, PhD.
Identification number: 1954
University e-mail: stefan.kozak [at] stuba.sk
 
External colleague - Institute of Applied Informatics, Automation and Mechatronics (MTF)

Contacts     Lesson     Projects     Publications     
Bodies     Supervised theses     Conferences     

Basic information

Basic information about a final thesis

Type of thesis: Dissertation thesis
Thesis title:MODIFICATION OF CHOSEN OPTIMISATION METHODS FOR LEARNING PROCESSES
Written by (author): Ing. Richard Valo, PhD.
Department: Institute of Robotics and Cybernetics (FEEIT)
Thesis supervisor: prof. Ing. Štefan Kozák, PhD.
Opponent 1:doc. Ing. Peter Schreiber, CSc.
Opponent 2:prof. Ing. Juraj Spalek, PhD.
Final thesis progress:Final thesis was successfully defended.


Additional information

Additional information about the final thesis follows. Click on the language link to display the information in the desired language.

Language of final thesis:Slovak

Slovak        English

Title of the thesis:MODIFICATION OF CHOSEN OPTIMISATION METHODS FOR LEARNING PROCESSES
Summary:The intention of this dissertation is to design and develop methods and algorithms of modelling and control of linear and non-linear dynamic systems using forward artificial neural networks of perceptron type. A program system is designed and developed in Matlab 6.5, Matlab -- Simulink, which enables to model the dynamic system with variable modifications of optimalisation algorithms. The structure of a neural model is a forward multi-layered neural network of perceptron type whose parameters are set up by a learning process back-propagation. The theoretical part is verified on the case study. It also creates an educative tool used to compare algorithms for searching the minimum of a function within the neural networks and beyond them.
Key words:Artificial neural networks, training algorithms, identification, Levenberg and Marquardt, minimum conditionality change

Display and download files

To display the final thesis assignment form click on the Display the final thesis assignment form icon. The following icons - Final thesis, Thesis appendices, Supervisor's review, Opponent's review - relate to the final thesis and can be downloaded. They could be displayed on condition they have been inserted and are available publicly.

Display the assignment form

Parts of thesis with postponed release:

Final thesis (final thesis appendices) unlimited
Reviews for final thesis unlimited